[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79RYFM9ATWHM6HAXJ3D19WV":3,"skill-same:01M79RYFM9ATWHM6HAXJ3D19WV":52},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M79RYFM9ATWHM6HAXJ3D19WV","tk-studio-research",null,"Run a chartered research pass — survey the topics a charter scopes, grade every finding by evidence, land the findings in the run workspace, and emit observation events for recommendation-worthy ones. Use when the user says \"run the ecosystem watch\", \"tk research\", or a research job's invoke-skill directive names this skill.","thkennedy\u002Ftk-studio","thkennedy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4164502?v=4","01M79QZ8DMP5FF2HC6GS3S6FDF","Tim Kennedy","01M79QZ8EM9JBWJ15R5JNC4PW3",0,"MIT","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-research\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: tk-studio-research\ndescription: Run a chartered research pass — survey the topics a charter scopes, grade every finding by evidence, land the findings in the run workspace, and emit observation events for recommendation-worthy ones. Use when the user says \"run the ecosystem watch\", \"tk research\", or a research job's invoke-skill directive names this skill.\n---\n\n# tk-studio-research\n\nThe research half of the evolve loop's input engine (ST-6.4, AD-8: observe\nand log only — findings feed recommendations, they never trigger changes).\nThe deterministic core keeps a run honest at both ends: no charter, no run;\nno evidence grade, no finding.\n\n## Behavior (both modes)\n\n1. **Charter first.** The scope arrives in the payload (a job run carries it\n   at `target.payload.charter`); validate it before any research:\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fresearch.py\" charter --charter '{\"topics\": [\"...\"], \"sources\": [\"...\"]}'\n   ```\n\n   Topics and sources are required and non-empty — an unscoped \"go\n   research\" ends `blocked` (headless) or asks once for scope (attended).\n\n2. **Seed the run (when anchors matter).** If the run's findings will cite\n   or correct standing assumptions, author a per-run seed and land it\n   through the core before researching (knowledge.schema.json shape —\n   `tier: seed`, the verbatim supersede header, `[SEED-\u003Crun-id>-A\u003Cn>]`\n   anchors, `inherits:` listing any project-spine anchors reused):\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fresearch.py\" seed --directory \u003Croot> --run-id \u003Crid> --file \u003Cseed.md>\n   ```\n\n   The core validates via `lib\u002Fknowledge.py`, verifies `inherits` against\n   the project spine when one exists, and reports a missing spine without\n   blocking — aid, not gate. A run that cites no anchors needs no seed.\n\n3. **Research within budget.** Survey the chartered topics through the\n   chartered sources only. When running as a job (an `invoke-skill`\n   directive from tk-studio-job), call `jobrun.py account --turns 1` every\n   iteration and stop the moment it answers `within_budget: false`. Cap\n   output at the charter's `max_findings` — depth beats sprawl.\n\n4. **Grade everything.** Every finding carries an evidence grade and its\n   trail: **A** primary source, verified directly; **B** multiple\n   independent sources agree; **C** single credible source; **D** inference\n   or speculation. A finding worth acting on carries a `recommendation`\n   with a concrete action. A finding about a seeded assumption cites it:\n   optional `anchor` = a bare anchor id from the seed's available set\n   (defined + inherited) — dangling citations are named rejections.\n\n5. **Land and emit through the core** (never hand-write the artifacts):\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fresearch.py\" record --directory \u003Croot> --run-id \u003Crid> --findings-file \u003Cfindings.json>\n   ```\n\n   The core validates the grades (and any anchor citations against the\n   seed), lands `findings.json` + `findings.md` in the run workspace,\n   reports project-spine presence, and emits one `observation` event per\n   recommendation-carrying finding (source `research-job`) — this surface's\n   own events; the job wrapper's `job-run` event stays the wrapper's\n   (AD-12). Then end the run via `jobrun.py finish`.\n\n6. **Attended:** summarize the graded findings and where they landed.\n   **Headless:** a missing\u002Finvalid charter ends `blocked`, a budget hit\n   ends `partial` with the guard named — never a prompt (AD-11). End\n   headless runs with the status block:\n\n   ```json\n   {\"status\": \"complete\", \"intent\": \"tk-studio-research\", \"artifacts\": [\"findings.json\", \"findings.md\"], \"reason\": null}\n   ```\n\nIf the deterministic core is unrunnable — a tool call denied by permissions, `uv`\u002Fpython unavailable — end `blocked` with the status block naming the unrunnable core as `reason`: never a question, never a headless run that ends without the block (AD-11).\n\n## The spine flavor (project scope)\n\nA chartered research run may be charged with authoring or growing the\n**project research spine** — the broad once-per-project assumption map that\nseeds inherit. Same discipline, different scope: research the project's\nactual systems and invariants within the charter, then land through the\ncore (never hand-write into the store):\n\n```bash\nuv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fresearch.py\" spine --directory \u003Croot> --run-id \u003Crid> --file \u003Cspine.md>\n```\n\nThe artifact carries `tier: spine`, the verbatim supersede header, and\n`[SPINE-A\u003Cn>]` anchors; it lands at `~\u002F.tk-studio\u002Fprojects\u002F\u003Ckey>\u002Fknowledge\u002Fspine.md`\n(per-user store, D2 — provisional knowledge never lands on the project\nVCS). Anchor ids are append-only: re-authoring must keep every existing\nid, or the core refuses — queued deltas cite identity.\n\n## Rules\n\n- Observe and log is the boundary (AD-8): findings and observations only —\n  never draft skills, edit configs, or open PRs from a research run.\n- Ungraded or evidence-free claims don't land: grades A–C require a\n  non-empty evidence trail; only D may stand bare, marked speculative.\n- Recommendation-worthy = carries a concrete `recommendation.action`; that\n  is what emits an observation, nothing else.\n- All paths resolve through `${CLAUDE_PLUGIN_ROOT}`.\n","# tk-studio-research\n\nThe research half of the evolve loop's input engine (ST-6.4, AD-8: observe\nand log only — findings feed recommendations, they never trigger changes).\nThe deterministic core keeps a run honest at both ends: no charter, no run;\nno evidence grade, no finding.\n\n## Behavior (both modes)\n\n1. **Charter first.** The scope arrives in the payload (a job run carries it\n   at `target.payload.charter`); validate it before any research:\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fresearch.py\" charter --charter '{\"topics\": [\"...\"], \"sources\": [\"...\"]}'\n   ```\n\n   Topics and sources are required and non-empty — an unscoped \"go\n   research\" ends `blocked` (headless) or asks once for scope (attended).\n\n2. **Seed the run (when anchors matter).** If the run's findings will cite\n   or correct standing assumptions, author a per-run seed and land it\n   through the core before researching (knowledge.schema.json shape —\n   `tier: seed`, the verbatim supersede header, `[SEED-\u003Crun-id>-A\u003Cn>]`\n   anchors, `inherits:` listing any project-spine anchors reused):\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fresearch.py\" seed --directory \u003Croot> --run-id \u003Crid> --file \u003Cseed.md>\n   ```\n\n   The core validates via `lib\u002Fknowledge.py`, verifies `inherits` against\n   the project spine when one exists, and reports a missing spine without\n   blocking — aid, not gate. A run that cites no anchors needs no seed.\n\n3. **Research within budget.** Survey the chartered topics through the\n   chartered sources only. When running as a job (an `invoke-skill`\n   directive from tk-studio-job), call `jobrun.py account --turns 1` every\n   iteration and stop the moment it answers `within_budget: false`. Cap\n   output at the charter's `max_findings` — depth beats sprawl.\n\n4. **Grade everything.** Every finding carries an evidence grade and its\n   trail: **A** primary source, verified directly; **B** multiple\n   independent sources agree; **C** single credible source; **D** inference\n   or speculation. A finding worth acting on carries a `recommendation`\n   with a concrete action. A finding about a seeded assumption cites it:\n   optional `anchor` = a bare anchor id from the seed's available set\n   (defined + inherited) — dangling citations are named rejections.\n\n5. **Land and emit through the core** (never hand-write the artifacts):\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fresearch.py\" record --directory \u003Croot> --run-id \u003Crid> --findings-file \u003Cfindings.json>\n   ```\n\n   The core validates the grades (and any anchor citations against the\n   seed), lands `findings.json` + `findings.md` in the run workspace,\n   reports project-spine presence, and emits one `observation` event per\n   recommendation-carrying finding (source `research-job`) — this surface's\n   own events; the job wrapper's `job-run` event stays the wrapper's\n   (AD-12). Then end the run via `jobrun.py finish`.\n\n6. **Attended:** summarize the graded findings and where they landed.\n   **Headless:** a missing\u002Finvalid charter ends `blocked`, a budget hit\n   ends `partial` with the guard named — never a prompt (AD-11). End\n   headless runs with the status block:\n\n   ```json\n   {\"status\": \"complete\", \"intent\": \"tk-studio-research\", \"artifacts\": [\"findings.json\", \"findings.md\"], \"reason\": null}\n   ```\n\nIf the deterministic core is unrunnable — a tool call denied by permissions, `uv`\u002Fpython unavailable — end `blocked` with the status block naming the unrunnable core as `reason`: never a question, never a headless run that ends without the block (AD-11).\n\n## The spine flavor (project scope)\n\nA chartered research run may be charged with authoring or growing the\n**project research spine** — the broad once-per-project assumption map that\nseeds inherit. Same discipline, different scope: research the project's\nactual systems and invariants within the charter, then land through the\ncore (never hand-write into the store):\n\n```bash\nuv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fresearch.py\" spine --directory \u003Croot> --run-id \u003Crid> --file \u003Cspine.md>\n```\n\nThe artifact carries `tier: spine`, the verbatim supersede header, and\n`[SPINE-A\u003Cn>]` anchors; it lands at `~\u002F.tk-studio\u002Fprojects\u002F\u003Ckey>\u002Fknowledge\u002Fspine.md`\n(per-user store, D2 — provisional knowledge never lands on the project\nVCS). Anchor ids are append-only: re-authoring must keep every existing\nid, or the core refuses — queued deltas cite identity.\n\n## Rules\n\n- Observe and log is the boundary (AD-8): findings and observations only —\n  never draft skills, edit configs, or open PRs from a research run.\n- Ungraded or evidence-free claims don't land: grades A–C require a\n  non-empty evidence trail; only D may stand bare, marked speculative.\n- Recommendation-worthy = carries a concrete `recommendation.action`; that\n  is what emits an observation, nothing else.\n- All paths resolve through `${CLAUDE_PLUGIN_ROOT}`.\n",{"name":5,"description":7},"main","ecd23b3c0458cd511812f643d9111e3d7c8235f4","plugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-research","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio","https:\u002F\u002Fgithub.com\u002Fthkennedy","https:\u002F\u002Ftimothyhkennedy.com","Just a guy who loves making tools, automation and games.","2026-11-10 20:38:16",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add thkennedy\u002Ftk-studio --skill tk-studio-research",{"tool":38,"command":39},"bunx","bunx skills add thkennedy\u002Ftk-studio --skill tk-studio-research",{"tool":41,"command":42},"pnpm","pnpm dlx skills add thkennedy\u002Ftk-studio --skill tk-studio-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-research\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"customize.toml","OTHER","其他",575,"https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-research\u002Fcustomize.toml",[53,60,67,74,81,88],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M79RYSQ8C3MWDFTDSRAYFJYA","tk-studio-track","Tracking verbs on the bound Jira project — `block` moves a story the loop cannot progress, and each dependent story, to \"Blocked - Awaiting User\" with a comment that @mentions the owner (or, with `--engagement`, one engagement's questions issue, which `close` later moves to \"Done\"); `reply` posts the owner's answer (or \"Done.\") with the owner's host-only token and moves the issue to \"Block Resolved\"; `validate` checks that resolution and passes the issue back to work or re-blocks it with a follow-up. Use when the user says \"block this story\", \"tk track block\", \"put it in the owner's inbox\", \"reply to the blocked issue\", \"validate the resolution\", or a supervisor or engagement payload names this skill.","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-track\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M79RYMVE0031EV5B64MBGD8V","tk-studio-session","Session discipline as a surface — land a boundary handoff (optionally carrying knowledge deltas) and end the session, or resume a fresh session from a run workspace alone. Use when the user says \"hand off this run\", \"tk session\", \"resume the run\", or a boundary\u002Fbudget trigger says the session must split.","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-session\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M79RYA1AWZZF83KBHGR6JDN3","tk-studio-report","One-verb human defect report — \"the skill did the wrong thing\" — recorded as a report event in the local measurement ledger. Use when the user says \"tk report\", \"report a defect\", \"that skill misbehaved\", or \"log a studio issue\".","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-report\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M79RY33VMYR5YNPVFKWRNW9S","tk-studio-playable-judge","The playable-verify leg's screenshot judge (Story 34.3) — reads only a playable run's report.json and its frames, answers the fixed rubric (scene loaded, player visible and framed, no magenta or error overlay, HUD reads, the named moments shown) with pass or fail and findings each naming a frame and a rubric line. Driven headless by the supervisor's host leg on the project's sandbox tier; use when the payload names a playable `media` folder, or the user says \"judge the playable frames\".","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-playable-judge\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M79RXY4AM8JM6ZK2MAR3W3X2","tk-studio-plan-sync","Planning adapter — canonicalize BMad-native planning artifacts (normalize pass, sole id authority) and sync them with the bound planning backend. Use when the user says \"sync the plan\", \"normalize planning artifacts\", \"tk plan sync\", or after stock BMad planning flows produce or change epics\u002Fstories.","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-plan-sync\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M79RXRDV34SQ7160973XEZ1A","tk-studio-orchestrator","The studio's front door — resolve who you are (role, per-user store), what this project needs (confirmed working_set.\u003Crole>), and route to resources by name, statelessly. Use when the user says \"enter the studio\", \"tk studio\", \"orchestrate\", \"convene the council\", or asks what to work on through the studio.","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-orchestrator\u002FSKILL.md",[],[]]